trends.barnas.net

benchmark · first seen 16 Oct 2026

ToolSandbox

A benchmark for evaluating tool-using language model agents in stateful, multi-turn interactive scenarios.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

learning to rankcounterfactual data generation for agent decision-making